Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add talayash/spring-fleet/plugin install spring-fleetWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/talayash/spring-fleet/federating-mcp-servers)<a href="https://agentmods.dev/skills/talayash/spring-fleet/federating-mcp-servers"><img src="https://agentmods.dev/badge/skills/talayash/spring-fleet/federating-mcp-servers.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00056 | $0.00843 |
| Opus 5 | $0.00028 | $0.00421 |
| Sonnet 5 | $0.00011 | $0.00169 |
| Haiku 4.5 | $0.00006 | $0.00084 |
Grade A, and why
federating-mcp-servers scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Federating fleet-owned MCP servers
Spring AI 1.1 ships spring-ai-starter-mcp-server-{webmvc,webflux,servlet},
so any Spring Boot service in the fleet can expose @Tool-annotated beans
(and selected actuator endpoints) as MCP tools. When that happens, the
right move is not to re-implement those tools inside spring-fleet — it is to
federate them: register each service's MCP server alongside the
spring-fleet MCP server so Claude sees one unified tool surface across the
whole fleet.
When to use
/fleet-init records services[].stack.springAiMcpServer = true for any
repo whose build declares spring-ai-starter-mcp-server. That flag is your
signal.
Procedure
-
Discover the candidates. Iterate
services[]and collect every one withstack.springAiMcpServer == true. For each, you need:- the transport URL (Streamable HTTP is the recommended 2026 transport;
SSE is being sunset). The default Spring AI MCP server endpoint is
http://<host>:<port><contextPath>/mcp. Confirm from each service'sapplication.propertiesifspring.ai.mcp.server.base-pathis set. - any required auth header (often a bearer token from the team's IDP).
- the transport URL (Streamable HTTP is the recommended 2026 transport;
SSE is being sunset). The default Spring AI MCP server endpoint is
-
Register them in the user's MCP client config. Claude Code reads
.mcp.json. Append one entry per federated server next to the existingspring-fleetentry, e.g.:{ "mcpServers": { "spring-fleet": { "command": "python", "args": ["${CLAUDE_PLUGIN_ROOT}/scripts/mcp_server.py"] }, "fleet-inventory": { "transport": "streamable-http", "url": "http://localhost:8083/inventory-v1/mcp" }, "fleet-order": { "transport": "streamable-http", "url": "http://localhost:8081/order-v1/mcp" } } }Always prefix the federated server name with
fleet-so the namespace is readable and collisions with non-fleet MCP servers are unlikely. -
Confirm with the user before editing
.mcp.json. Federation changes the agent's effective tool surface and the data it can read — that's a shared-state change worth a quick confirmation. Show the proposed diff.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 72 lines · 56 tokens per session scan A f91da72d2c3f
federating-mcp-servers is a skill published in the GitHub repository talayash/spring-fleet (2 stars, last pushed 2mo ago), licensed MIT. It adds 56 tokens to every session and 843 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
logging-standards
Structured logging standards: log levels, structured fields, correlation IDs, PII masking, and event naming. TRIGGER when: adding log statements, configuring loggers, or reviewing log output. SKIP: metrics and alerting (use monitoring-observability); error control flow (use error-handling). (Examples use structlog +…
mui-styling
Material-UI (MUI) styling standards: sx-prop priority, theme tokens, spacing scale, responsive design, and accessibility. TRIGGER when: styling MUI components, defining theme tokens, or building responsive layouts. SKIP: component logic and hooks (use react-patterns); cross-stack UX/design decisions (use…
sofa-search
Search Stack Overflow for Agents (SOFA) for a peer-verified solution before solving from scratch. TRIGGER when: about to debug an unfamiliar error, integrate a new API/library, or research an unfamiliar pattern, and SOFA is configured. SKIP: trivial/familiar tasks; SOFA unconfigured (no-op); contributing (future…
watch-patterns
Correct construction of watchers for long-running operations. TRIGGER when: arming observation of a long-running operation (CI run, deploy, transfer, GC/prune, log stream), writing poll/until loops, or using the Monitor tool. SKIP: defining production alerts/metrics (use monitoring-observability); log formatting (use…
agent-memory
3-tier markdown memory protocol (shared/agent/conversation) for cross-session knowledge. TRIGGER when: reading or writing agent memory files, choosing which memory tier an insight belongs in, or starting a task needing prior context. SKIP: vector recall (use semantic-memory-mcp); distilling conversations into…
database-optimization
Schema design, index strategy, migration safety, and query analysis. TRIGGER when: designing tables or indexes, writing a migration, or diagnosing a slow query. SKIP: writing ORM model code (use python-patterns); generic backend patterns (use python-patterns).